public model

config.json

@@ -0,0 +1,76 @@
+{
+  "_name_or_path": "AutoNLP",
+  "activation_dropout": 0.0,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "conv_bias": true,
+  "conv_dim": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2
+  ],
+  "conv_stride": [
+    5,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "ctc_loss_reduction": "mean",
+  "ctc_zero_infinity": false,
+  "do_stable_layer_norm": true,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_dropout": 0.0,
+  "feat_extract_norm": "layer",
+  "feat_proj_dropout": 0.05,
+  "final_dropout": 0.0,
+  "gradient_checkpointing": true,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.1,
+  "mask_channel_length": 10,
+  "mask_channel_min_space": 1,
+  "mask_channel_other": 0.0,
+  "mask_channel_prob": 0.0,
+  "mask_channel_selection": "static",
+  "mask_feature_length": 10,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_space": 1,
+  "mask_time_other": 0.0,
+  "mask_time_prob": 0.05,
+  "mask_time_selection": "static",
+  "model_type": "wav2vec2",
+  "num_attention_heads": 16,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 24,
+  "pad_token_id": 71,
+  "transformers_version": "4.4.1",
+  "vocab_size": 73
+}

preprocessor_config.json

@@ -0,0 +1,8 @@
+{
+  "do_normalize": true,
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc828dbd86f2e9421081ea47aadb010f5edb9edc38ef42f9e5ed4919552aa431
+size 1262233111

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|"}

vocab.json

@@ -0,0 +1 @@
+{"ठ": 0, "ब": 1, "ट": 2, "ज़": 3, "फ़": 4, "ड": 5, "ष": 6, "ो": 8, "उ": 9, "भ": 10, "ई": 11, "ख": 12, "ढ": 13, "ख़": 14, "म": 15, "औ": 16, "क": 17, "क़": 18, "घ": 19, "ॠ": 20, "ौ": 21, "च": 22, "अ": 23, "आ": 24, "ञ": 25, "ड़": 26, "ॉ": 27, "ा": 28, "ि": 29, "प": 30, "ी": 31, "ग": 32, "ं": 33, "श": 34, "ढ़": 35, "ऍ": 36, "ऐ": 37, "र": 38, "ु": 39, "न": 40, "ऋ": 41, "ल": 42, "े": 43, "ृ": 44, "ै": 45, "ओ": 46, "ँ": 47, "ऑ": 48, "ह": 49, "छ": 50, "ण": 51, "ू": 52, "झ": 53, "त": 54, "स": 55, "व": 56, "ग़": 57, "य": 58, "ज": 59, "ध": 60, "ए": 61, "फ": 62, "़": 63, "द": 64, "ः": 65, "इ": 66, "थ": 67, "ऊ": 68, "्": 69, "|": 7, "[UNK]": 70, "[PAD]": 71}